© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3753
    Prev
    Next
    INDEX
    Explanations

    mentions of artists

    oai_token-act-pair · gemini-2.0-flash

    Information/Facts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     works
    -0.68
    reggio
    -0.51
     WORKS
    -0.49
     wund
    -0.49
    Contributed
    -0.48
     maquina
    -0.47
    voř
    -0.46
    ortions
    -0.45
    نجليزية
    -0.45
     obras
    -0.45
    POSITIVE LOGITS
     виправивши
    0.81
     estekak
    0.67
    NOPQRST
    0.63
    IVEREF
    0.63
     kaynağından
    0.63
    Personensuche
    0.62
    LookAnd
    0.55
    )";
    0.55
    πως
    0.53
    PreferredItem
    0.53
    Activations Density 0.291%

    No Known Activations